def test_bam(self):
bamFile = os.path.join(big_data_dir, "Hpyl_1_5000.bam")
refFile = os.path.join(ref_dir, "Helicobacter_pylori_J99", "sequence",
"Helicobacter_pylori_J99.fasta")
ds = AlignmentSet(bamFile, referenceFastaFname=refFile)
contigs = ReferenceUtils.loadReferenceContigs(refFile, ds)
self.assertEquals(len(contigs), 1)
self.assertEquals(contigs[0].cmph5ID, 0)
chemistry = ReferenceUtils.loadAlignmentChemistry(ds)
self.assertEquals(chemistry, "P6-C4")
def loadReferenceAndModel(self, referencePath, ipdModelFilename):
assert self.alignments is not None and self.referenceWindows is not None
# Load the reference contigs - annotated with their refID from the cmp.h5
logging.info("Loading reference contigs {!r}".format(referencePath))
contigs = ReferenceUtils.loadReferenceContigs(
referencePath,
alignmentSet=self.alignments,
windows=self.referenceWindows)
self.ipdModel = IpdModel(contigs, ipdModelFilename,
self.args.modelIters)
def test_bam (self):
bamFile = os.path.join(big_data_dir, "Hpyl_1_5000.bam")
refFile = os.path.join(ref_dir, "Helicobacter_pylori_J99", "sequence",
"Helicobacter_pylori_J99.fasta")
ds = AlignmentSet(bamFile, referenceFastaFname=refFile)
contigs = ReferenceUtils.loadReferenceContigs(refFile, ds)
self.assertEquals(len(contigs), 1)
self.assertEquals(contigs[0].cmph5ID, 0)
chemistry = ReferenceUtils.loadAlignmentChemistry(ds)
self.assertEquals(chemistry, "P6-C4")
def test_cmph5(self):
base_dir = os.path.dirname(os.path.abspath(__file__))
dataDir = os.path.join(base_dir, 'data')
resourcesDir = os.path.join(base_dir, '../kineticsTools/resources')
refFile = os.path.join(dataDir, 'lambda', 'sequence', 'lambda.fasta')
cmpFile = os.path.join(dataDir, "p4-c2-lambda-mod-decode.cmp.h5")
ds = AlignmentSet(cmpFile, referenceFastaFname=refFile)
contigs = ReferenceUtils.loadReferenceContigs(refFile, ds)
self.assertEquals(len(contigs), 1)
self.assertEquals(contigs[0].cmph5ID, 1)
chemistry = ReferenceUtils.loadAlignmentChemistry(ds)
self.assertEquals(chemistry, "P4-C2")
def test_cmph5 (self):
base_dir = os.path.dirname(os.path.abspath(__file__))
dataDir = os.path.join(base_dir,'data')
resourcesDir = os.path.join(base_dir, '../kineticsTools/resources')
refFile = os.path.join(dataDir, 'lambda', 'sequence', 'lambda.fasta')
cmpFile = os.path.join(dataDir, "p4-c2-lambda-mod-decode.cmp.h5")
ds = AlignmentSet(cmpFile, referenceFastaFname=refFile)
contigs = ReferenceUtils.loadReferenceContigs(refFile, ds)
self.assertEquals(len(contigs), 1)
self.assertEquals(contigs[0].cmph5ID, 1)
chemistry = ReferenceUtils.loadAlignmentChemistry(ds)
self.assertEquals(chemistry, "P4-C2")
def loadReferenceAndModel(self, referencePath):
assert self.alignments is not None and self.referenceWindows is not None
# Load the reference contigs - annotated with their refID from the cmp.h5
logging.info("Loading reference contigs %s" % referencePath)
contigs = ReferenceUtils.loadReferenceContigs(referencePath,
alignmentSet=self.alignments, windows=self.referenceWindows)
# There are three different ways the ipdModel can be loaded.
# In order of precedence they are:
# 1. Explicit path passed to --ipdModel
# 2. Path to parameter bundle, model selected using the cmp.h5's sequencingChemistry tags
# 3. Fall back to built-in model.
# By default, use built-in model
ipdModel = None
if self.args.ipdModel:
ipdModel = self.args.ipdModel
logging.info("Using passed in ipd model: %s" % self.args.ipdModel)
if not os.path.exists(self.args.ipdModel):
logging.error("Couldn't find model file: %s" % self.args.ipdModel)
sys.exit(1)
elif self.args.paramsPath:
if not os.path.exists(self.args.paramsPath):
logging.error("Params path doesn't exist: %s" % self.args.paramsPath)
sys.exit(1)
majorityChem = ReferenceUtils.loadAlignmentChemistry(self.alignments)
# Temporary solution for Sequel chemistries: we do not
# have trained kinetics models in hand yet for Sequel
# chemistries. However we have observed that the P5-C3
# training seems to yield fairly good results on Sequel
# chemistries to date. So for the moment, we will use
# that model for Sequel data.
if majorityChem.startswith("S/"):
logging.info("No trained model available yet for Sequel chemistries; modeling as P5-C3")
majorityChem = "P5-C3"
ipdModel = os.path.join(self.args.paramsPath, majorityChem + ".h5")
if majorityChem == 'unknown':
logging.error("Chemistry cannot be identified---cannot perform kinetic analysis")
sys.exit(1)
elif not os.path.exists(ipdModel):
logging.error("Aborting, no kinetics model available for this chemistry: %s" % ipdModel)
sys.exit(1)
else:
logging.info("Using Chemistry matched IPD model: %s" % ipdModel)
self.ipdModel = IpdModel(contigs, ipdModel, self.args.modelIters)
def loadReferenceAndModel(self, referencePath, cmpH5Path):
# Load the reference contigs - annotated with their refID from the cmp.h5
contigs = ReferenceUtils.loadReferenceContigs(referencePath, cmpH5Path)
# Read reference info table from cmp.h5
(refInfoTable, _) = ReferenceUtils.loadCmpH5Tables(cmpH5Path)
self.refInfo = refInfoTable
# There are three different ways the ipdModel can be loaded.
# In order of precedence they are:
# 1. Explicit path passed to --ipdModel
# 2. Path to parameter bundle, model selected using the cmp.h5's chemistry info
# 3. Fall back to built-in model.
# By default, use built-in model
ipdModel = None
if self.args.ipdModel:
ipdModel = self.args.ipdModel
logging.info("Using passed in ipd model: %s" % self.args.ipdModel)
if not os.path.exists(self.args.ipdModel):
logging.error("Couldn't find model file: %s" %
self.args.ipdModel)
elif self.args.paramsPath:
if not os.path.exists(self.args.paramsPath):
logging.error("Params path doesn't exist: %s" %
self.args.paramsPath)
sys.exit(1)
majorityChem = ReferenceUtils.loadCmpH5Chemistry(cmpH5Path)
ipdModel = os.path.join(self.args.paramsPath, majorityChem + ".h5")
if majorityChem == 'unknown':
logging.warning(
"Chemistry is unknown. Falling back to built-in model")
ipdModel = None
elif not os.path.exists(ipdModel):
logging.warning("Model not found: %s" % ipdModel)
logging.warning("Falling back to built-in model")
ipdModel = None
else:
logging.info("Using Chemistry matched IPD model: %s" %
ipdModel)
self.ipdModel = IpdModel(contigs, ipdModel, self.args.modelIters)
def setUp(self):
self.cmpH5 = None
resourcesDir = os.path.join(os.path.dirname(os.path.abspath(__file__)), '../kineticsTools/resources')
ref = self.getReference()
alnFile = self.getAlignments()
assert os.path.exists(alnFile) and os.path.exists(ref)
self.ds = AlignmentSet(alnFile, referenceFastaFname=ref)
self.contigs = ReferenceUtils.loadReferenceContigs(ref, self.ds)
self.ipdModel = IpdModel(self.contigs, os.path.join(resourcesDir, "P6-C4.h5"))
# Create a functional KineticWorker object that can be poked at
self.kw = KineticWorker(self.ipdModel)
# Put in our cmp.h5 - this is normally supplied by the Worker
self.kw.caseCmpH5 = self.ds
self.kw.controlCmpH5 = None
self.kw.options = self.getOpts()
def setUp(self):
self.cmpH5 = None
resourcesDir = os.path.join(os.path.dirname(os.path.abspath(__file__)),
'../kineticsTools/resources')
ref = self.getReference()
alnFile = self.getAlignments()
assert os.path.exists(alnFile) and os.path.exists(ref)
self.ds = AlignmentSet(alnFile, referenceFastaFname=ref)
self.contigs = ReferenceUtils.loadReferenceContigs(ref, self.ds)
self.ipdModel = IpdModel(self.contigs,
os.path.join(resourcesDir, "P6-C4.h5"))
# Create a functional KineticWorker object that can be poked at
self.kw = KineticWorker(self.ipdModel)
# Put in our cmp.h5 - this is normally supplied by the Worker
self.kw.caseCmpH5 = self.ds
self.kw.controlCmpH5 = None
self.kw.options = self.getOpts()
def loadReferenceAndModel(self, referencePath, cmpH5Path):
# Load the reference contigs - annotated with their refID from the cmp.h5
contigs = ReferenceUtils.loadReferenceContigs(referencePath, cmpH5Path)
# Read reference info table from cmp.h5
(refInfoTable, _) = ReferenceUtils.loadCmpH5Tables(cmpH5Path)
self.refInfo = refInfoTable
# There are three different ways the ipdModel can be loaded.
# In order of precedence they are:
# 1. Explicit path passed to --ipdModel
# 2. Path to parameter bundle, model selected using the cmp.h5's chemistry info
# 3. Fall back to built-in model.
# By default, use built-in model
ipdModel = None
if self.args.ipdModel:
ipdModel = self.args.ipdModel
logging.info("Using passed in ipd model: %s" % self.args.ipdModel)
if not os.path.exists(self.args.ipdModel):
logging.error("Couldn't find model file: %s" % self.args.ipdModel)
elif self.args.paramsPath:
if not os.path.exists(self.args.paramsPath):
logging.error("Params path doesn't exist: %s" % self.args.paramsPath)
sys.exit(1)
majorityChem = ReferenceUtils.loadCmpH5Chemistry(cmpH5Path)
ipdModel = os.path.join(self.args.paramsPath, majorityChem + ".h5")
if majorityChem == "unknown":
logging.warning("Chemistry is unknown. Falling back to built-in model")
ipdModel = None
elif not os.path.exists(ipdModel):
logging.warning("Model not found: %s" % ipdModel)
logging.warning("Falling back to built-in model")
ipdModel = None
else:
logging.info("Using Chemistry matched IPD model: %s" % ipdModel)
self.ipdModel = IpdModel(contigs, ipdModel, self.args.modelIters)
def setUp(self):
# Load the lambda genome from our sample data
dataDir = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'data')
ref = os.path.join(dataDir, 'lambda', 'sequence', 'lambda.fasta')
cmpFile = os.path.join(dataDir, "p4-c2-lambda-mod-decode.cmp.h5")
self.contigs = ReferenceUtils.loadReferenceContigs(ref, cmpFile)
self.ipdModel = IpdModel(self.contigs)
# Create a functional KineticWorker object that can be poked at manually.
self.kw = KineticWorker(self.ipdModel)
self.cmpH5 = CmpH5Reader(cmpFile)
# Put in our cmp.h5 - this is normally supplied by the Worker superclass
self.kw.caseCmpH5 = self.cmpH5
self.kw.controlCmpH5 = None
self.kw.options = self.getOpts()
def setUp(self):
# Load the lambda genome from our sample data
dataDir = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'data')
resourcesDir = os.path.join(os.path.dirname(os.path.abspath(__file__)), '../kineticsTools/resources')
ref = os.path.join(dataDir, 'lambda', 'sequence', 'lambda.fasta')
cmpFile = os.path.join(dataDir, "p4-c2-lambda-mod-decode.cmp.h5")
self.cmpH5 = AlignmentSet(cmpFile, referenceFastaFname=ref)
self.contigs = ReferenceUtils.loadReferenceContigs(ref, self.cmpH5)
self.ipdModel = IpdModel(self.contigs, os.path.join(resourcesDir, "P4-C2.h5"))
# Create a functional KineticWorker object that can be poked at manually.
self.kw = KineticWorker(self.ipdModel)
# Put in our cmp.h5 - this is normally supplied by the Worker superclass
self.kw.caseCmpH5 = self.cmpH5
self.kw.controlCmpH5 = None
self.kw.options = self.getOpts()
def loadReferenceAndModel(self, referencePath):
assert self.alignments is not None and self.referenceWindows is not None
# Load the reference contigs - annotated with their refID from the cmp.h5
logging.info("Loading reference contigs %s" % referencePath)
contigs = ReferenceUtils.loadReferenceContigs(referencePath,
alignmentSet=self.alignments, windows=self.referenceWindows)
# There are three different ways the ipdModel can be loaded.
# In order of precedence they are:
# 1. Explicit path passed to --ipdModel
# 2. Path to parameter bundle, model selected using the cmp.h5's sequencingChemistry tags
# 3. Fall back to built-in model.
# By default, use built-in model
ipdModel = None
if self.args.ipdModel:
ipdModel = self.args.ipdModel
logging.info("Using passed in ipd model: %s" % self.args.ipdModel)
if not os.path.exists(self.args.ipdModel):
logging.error("Couldn't find model file: %s" % self.args.ipdModel)
sys.exit(1)
elif self.args.paramsPath:
if not os.path.exists(self.args.paramsPath):
logging.error("Params path doesn't exist: %s" % self.args.paramsPath)
sys.exit(1)
majorityChem = ReferenceUtils.loadAlignmentChemistry(self.alignments)
ipdModel = os.path.join(self.args.paramsPath, majorityChem + ".h5")
if majorityChem == 'unknown':
logging.error("Chemistry cannot be identified---cannot perform kinetic analysis")
sys.exit(1)
elif not os.path.exists(ipdModel):
logging.error("Aborting, no kinetics model available for this chemistry: %s" % ipdModel)
sys.exit(1)
else:
logging.info("Using Chemistry matched IPD model: %s" % ipdModel)
self.ipdModel = IpdModel(contigs, ipdModel, self.args.modelIters)
def loadReferenceAndModel(self, referencePath, cmpH5Path):
# Load the reference contigs - annotated with their refID from the cmp.h5
contigs = ReferenceUtils.loadReferenceContigs(referencePath, cmpH5Path)
# Read reference info table from cmp.h5
(refInfoTable, _) = ReferenceUtils.loadCmpH5Tables(cmpH5Path)
if (self.options.refContigs is not None
or self.options.refContigIndex != -1):
if (self.options.refContigs is not None
and self.options.refContigIndex != -1):
requestedIds = set(self.options.refContigs.split(',')).union(
[self.options.refContigIndex])
elif (self.options.refContigs is None
and self.options.refContigIndex != -1):
requestedIds = set([self.options.refContigIndex])
elif (self.options.refContigs is not None
and self.options.refContigIndex == -1):
requestedIds = set(self.options.refContigs.split(','))
relevantContigs = [
i for (i, rec) in enumerate(refInfoTable)
if (rec.FullName in requestedIds or rec.Name in requestedIds
or rec.RefInfoID in requestedIds)
]
self.refInfo = refInfoTable[relevantContigs]
else:
self.refInfo = refInfoTable
# There are three different ways the ipdModel can be loaded.
# In order of precedence they are:
# 1. Explicit path passed to --ipdModel
# 2. Path to parameter bundle, model selected using the cmp.h5's sequencingChemistry tags
# 3. Fall back to built-in model.
# By default, use built-in model
ipdModel = None
if self.args.ipdModel:
ipdModel = self.args.ipdModel
logging.info("Using passed in ipd model: %s" % self.args.ipdModel)
if not os.path.exists(self.args.ipdModel):
logging.error("Couldn't find model file: %s" %
self.args.ipdModel)
sys.exit(1)
elif self.args.paramsPath:
if not os.path.exists(self.args.paramsPath):
logging.error("Params path doesn't exist: %s" %
self.args.paramsPath)
sys.exit(1)
majorityChem = ReferenceUtils.loadCmpH5Chemistry(cmpH5Path)
ipdModel = os.path.join(self.args.paramsPath, majorityChem + ".h5")
if majorityChem == 'unknown':
logging.error(
"Chemistry cannot be identified---cannot perform kinetic analysis"
)
sys.exit(1)
elif not os.path.exists(ipdModel):
logging.error(
"Aborting, no kinetics model available for this chemistry: %s"
% ipdModel)
sys.exit(1)
else:
logging.info("Using Chemistry matched IPD model: %s" %
ipdModel)
self.ipdModel = IpdModel(contigs, ipdModel, self.args.modelIters)
def loadReferenceAndModel(self, referencePath, cmpH5Path):
# Load the reference contigs - annotated with their refID from the cmp.h5
contigs = ReferenceUtils.loadReferenceContigs(referencePath, cmpH5Path)
# Read reference info table from cmp.h5
(refInfoTable, _) = ReferenceUtils.loadCmpH5Tables(cmpH5Path)
if (self.options.refContigs is not None or
self.options.refContigIndex != -1):
if (self.options.refContigs is not None and
self.options.refContigIndex != -1):
requestedIds = set(self.options.refContigs.split(',')).union([self.options.refContigIndex])
elif (self.options.refContigs is None and
self.options.refContigIndex != -1):
requestedIds = set([self.options.refContigIndex])
elif (self.options.refContigs is not None and
self.options.refContigIndex == -1):
requestedIds = set(self.options.refContigs.split(','))
relevantContigs = [ i for (i, rec) in enumerate(refInfoTable)
if (rec.FullName in requestedIds or
rec.Name in requestedIds or
rec.RefInfoID in requestedIds) ]
self.refInfo = refInfoTable[relevantContigs]
else:
self.refInfo = refInfoTable
# There are three different ways the ipdModel can be loaded.
# In order of precedence they are:
# 1. Explicit path passed to --ipdModel
# 2. Path to parameter bundle, model selected using the cmp.h5's sequencingChemistry tags
# 3. Fall back to built-in model.
# By default, use built-in model
ipdModel = None
if self.args.ipdModel:
ipdModel = self.args.ipdModel
logging.info("Using passed in ipd model: %s" % self.args.ipdModel)
if not os.path.exists(self.args.ipdModel):
logging.error("Couldn't find model file: %s" % self.args.ipdModel)
sys.exit(1)
elif self.args.paramsPath:
if not os.path.exists(self.args.paramsPath):
logging.error("Params path doesn't exist: %s" % self.args.paramsPath)
sys.exit(1)
majorityChem = ReferenceUtils.loadCmpH5Chemistry(cmpH5Path)
ipdModel = os.path.join(self.args.paramsPath, majorityChem + ".h5")
if majorityChem == 'unknown':
logging.warning("Chemistry is unknown. Falling back to built-in model")
ipdModel = None
elif not os.path.exists(ipdModel):
logging.warning("Model not found: %s" % ipdModel)
logging.warning("Falling back to built-in model")
ipdModel = None
else:
logging.info("Using Chemistry matched IPD model: %s" % ipdModel)
self.ipdModel = IpdModel(contigs, ipdModel, self.args.modelIters)